finding
active
finding:matched-perplexity-on-olmo-7b-k-fac-22-84-bsn-23-59-svd-22-49-baseline-19-04Matched perplexity on OLMo-7B: K-FAC 22.84, BSN 23.59, SVD 22.49 (baseline 19.04)
Coherence comparison.
Source paper
extracted_from(2025) · Merullo, Jack · Vatsavaya, Srihita · Bushnaq, Lucius · Lewis, Owen
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- K-FAC suppresses the broadest range of unseen memorized text without requiring labeled forget datasupportsPractical advantage over BSN.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Better transfer to unseen memorized data.
- Replication at smaller scale.
- Disentanglement evidence.
- K-FAC edit reduces OLMo-7B Dolma strict accuracy from 99.9% to 3.4% (BSN 6.0%, SVD 3.0%)finding0.790Table 1.
- Fig. 5.
- Validates robustness of alignment metric choice
- Domain-specific vulnerability comparison between architectures
- Moderate agreement.